58 citations · 147 across the 67 of their papers we have counts for
16 papers · 1 filter
RISA: Response Inspection and Selective Actions for Refusal Calibration in Large Language Models
Wenhan Chang, Tianqing Zhu, Ping Xiong +2
Reliable refusal behavior requires Large Language Models (LLMs) to reject harmful prompts with only answering benign ones. Incorrect refusal behavior can either expose users to har…
BASIS: Breach-Aware Selective Prompt Injection Shielding with Prefill Attention Probes
Laiqiao Qin, Tianqing Zhu, Longxiang Gao +1
Prompt injection is a critical security threat in large language model (LLM) applications, where attackers hijack model behavior by embedding malicious instructions in user or exte…
One Framework for All: Cross-Modal Membership Inference for Generative Models
Dayong Ye, Tainqing Zhu, Kun Gao +6
Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks. One fundamental threat is membership inf…
Auditing Machine Unlearning: A Systematic Research on Whether Models Truly Forget
Dayong Ye, Tianqing Zhu, Ruiding Huang +5
Machine unlearning has been extensively studied in response to growing privacy concerns and regulatory requirements. However, auditing whether unlearning algorithms have truly eras…
When LLMs Team Up: A Coordinated Attack Framework for Automated Cyber Intrusions
Minfeng Qi, Tianqing Zhu, Zijie Xu +3
Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance ofte…
CSC: Turning the Adversary's Poison against Itself
Yuchen Shi, Xin Guo, Huajie Chen +3
Poisoning-based backdoor attacks pose significant threats to deep neural networks by embedding triggers in training data, causing models to misclassify triggered inputs as adversar…
Unreal Thinking: Chain-of-Thought Hijacking via Two-stage Backdoor
Wenhan Chang, Tianqing Zhu, Ping Xiong +2
Large Language Models (LLMs) are increasingly deployed in settings where Chain-of-Thought (CoT) is interpreted by users. This creates a new safety risk: attackers may manipulate th…
Are LLMs Ready for Computer Science Education? A Cross-Domain, Cross-Lingual and Cognitive-Level Evaluation Using Professional Certification Exams
Chen Gao, Chi Liu, Zhengquan Luo +10
Large language models (LLMs) are increasingly applied in computer science education for tasks such as tutoring, content generation, and code assessment. However, systematic evaluat…
Secure Forgetting: A Framework for Privacy-Driven Unlearning in Large Language Model (LLM)-Based Agents
Dayong Ye, Tainqing Zhu, Congcong Zhu +5
Large language model (LLM)-based agents have recently gained considerable attention due to the powerful reasoning capabilities of LLMs. Existing research predominantly focuses on e…
Poisoning the Pixels: Revisiting Backdoor Attacks on Semantic Segmentation
Guangsheng Zhang, Huan Tian, Leo Zhang +4
Semantic segmentation models are widely deployed in safety-critical applications such as autonomous driving, yet their vulnerability to backdoor attacks remains largely underexplor…
Osmosis Distillation: Model Hijacking with the Fewest Samples
Yuchen Shi, Huajie Chen, Heng Xu +6
Transfer learning is devised to leverage knowledge from pre-trained models to solve new tasks with limited data and computational resources. Meanwhile, dataset distillation has eme…
From Spark to Fire: Modeling and Mitigating Error Cascades in LLM-Based Multi-Agent Collaboration
Yizhe Xie, Congcong Zhu, Xinyue Zhang +5
Large Language Model-based Multi-Agent Systems (LLM-MAS) are increasingly applied to complex collaborative scenarios. However, their collaborative mechanisms may cause minor inaccu…
Hide&Seek: Remove Image Watermarks with Negligible Cost via Pixel-wise Reconstruction
Huajie Chen, Tianqing Zhu, Hailin Yang +7
Watermarking has emerged as a key defense against the misuse of machine-generated images (MGIs). Yet the robustness of these protections remains underexplored. To reveal the limits…
Turning Black Box into White Box: Dataset Distillation Leaks
Huajie Chen, Tianqing Zhu, Yuchen Zhong +7
Dataset distillation compresses a large real dataset into a small synthetic one, enabling models trained on the synthetic data to achieve performance comparable to those trained on…
Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
Linlin Wang, Tianqing Zhu, Laiqiao Qin +2
With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated sing…
Forgetting Similar Samples: Can Machine Unlearning Do it Better?
Heng Xu, Tianqing Zhu, Dayong Ye +3
Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extens…